Model Context Protocol
Model Context Protocol is a standard way for AI applications to connect models with tools, data sources, and structured context.
Category
Agent Permission Design
These terms help describe safer AI agent workflows where access is scoped, recorded, and reviewable.
How to recognize this theme
AI agent control terms for tools, memory, and review steps.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Tool Call Allowlist
A tool call allowlist defines which tools or actions an AI agent may use during a workflow.
Agent Memory Store
An agent memory store keeps selected context that an AI agent can reuse across steps, sessions, or tasks under defined rules.
Approval Checkpoint
An approval checkpoint is a required review step before an AI agent can take a sensitive action or send an instruction to another system.